Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressing uncertainty or condition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     currency
    0.42
    ijl
    0.41
     rapids
    0.40
     creativity
    0.38
     indice
    0.38
     diffraction
    0.37
     idols
    0.37
     creative
    0.36
     modulus
    0.36
     intensify
    0.36
    POSITIVE LOGITS
    AcOH
    0.37
    Sec
    0.35
     jälkeen
    0.33
    癌症
    0.32
     මත
    0.31
     tämän
    0.31
     것처럼
    0.31
     stringWith
    0.30
     Except
    0.30
     Concerning
    0.30
    Act Density 0.001%

    No Known Activations